app.py

import os
import gradio as gr
import torch
from transformers import pipeline

print(f"Is CUDA available: {torch.cuda.is_available()}")
print(f"CUDA device: {torch.cuda.get_device_name(torch.cuda.current_device())}")

examples = [['COVID-19 is'],['A 65-year-old female patient with a past medical history of']] 

pipe_biogpt = pipeline("text-generation", model="microsoft/BioGPT-Large", device="cuda:0")

title = "BioGPT-Large Demo"
description = """
Check out the [BioGPT-Large model card](https://huggingface.co/microsoft/biogpt-large) for more info. 
**Disclaimer:** this demo was made for research purposes only and should not be used for medical purposes.
"""

def inference(text):
  output_biogpt = pipe_biogpt(text, max_length=100)[0]["generated_text"]
  return [
      output_biogpt, 
  ]

io = gr.Interface(
  inference,
  gr.Textbox(lines=3),
  outputs=[
    gr.Textbox(lines=3, label="BioGPT-Large"),
  ],
  title=title,
  description=description,
  examples=examples
)
io.launch()